© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3881
    Prev
    Next
    INDEX
    Explanations

    lottery tickets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Zulu
    1.88
     Duo
    1.77
     personalisation
    1.76
    ┆
    1.74
     taz
    1.72
    Linkedin
    1.67
    ZZ
    1.66
     nz
    1.65
    Kob
    1.65
    Benz
    1.64
    POSITIVE LOGITS
    boy
    1.23
     superblock
    1.19
    瞅
    1.15
    gesteld
    1.15
    AMINATION
    1.06
    americano
    1.05
    óle
    1.04
    ITT
    1.03
     olho
    1.02
    irmed
    1.02
    Activations Density 0.009%

    No Known Activations